Qwen-AgentWorld：面向通用智能體的語言世界模型

摘要

世界模型根據當前觀測與行動預測環境動態，作為推理與規劃的核心認知機制。本研究探討基於語言模型的世界建模如何進一步拓展通用智能體的邊界。（i）首先聚焦於建構智能體環境模擬的基礎模型。我們推出 Qwen-AgentWorld-35B-A3B 與 Qwen-AgentWorld-397B-A17B，這是首批能夠透過長思維鏈推理，模擬涵蓋七個領域的智能體環境的語言世界模型。利用真實環境中超過一千萬條、來自七個領域的環境互動軌跡，我們透過三階段訓練流程開發 Qwen-AgentWorld：CPT 階段從狀態轉移動態與增強的專業語料注入通用世界建模能力；SFT 階段啟動下一狀態預測推理；RL 階段則透過基於混合評分量表與規則獎勵的客製化框架，強化模擬保真度。為評估語言世界模型，我們提出 AgentWorldBench——一個基於五個前沿模型在九個既有基準的真實互動所建構的全面性基準測試。實證結果顯示，Qwen-AgentWorld 顯著優於現有前沿模型。（ii）超越基礎模型層面，我們進一步探討世界模型增強通用智能體的兩種互補典範。首先，作為解耦的環境模擬器，Qwen-AgentWorld 支援對數千個真實環境進行可擴展且可控的模擬，以進行智能體強化學習，其成效超越僅使用真實環境訓練的結果。其次，作為統一的智能體基礎模型，世界模型訓練扮演了高度有效的預熱階段，能改善七個智能體基準測試的下游表現。程式碼：https://github.com/QwenLM/Qwen-AgentWorld

English

A world model predicts environment dynamics based on current observations and actions, serving as a core cognitive mechanism for reasoning and planning. In this work, we investigate how world modeling based on language models can further push the boundaries of general agents. (i) We first focus on building foundation models for agentic environment simulation. We introduce Qwen-AgentWorld-35B-A3B and Qwen-AgentWorld-397B-A17B, the first language world models capable of simulating agentic environments covering 7 domains via long chain-of-thought reasoning. Leveraging more than 10M environment interaction trajectories of 7 domains in real-world environments, we develop Qwen-AgentWorld through a three-stage training pipeline: CPT injects general-purpose world modeling capabilities from the state transition dynamics and augmented professional corpora, SFT activates next-state-prediction reasoning, and RL sharpens simulation fidelity through a tailored framework with hybrid rubric-and-rule rewards. To evaluate language world models, we present AgentWorldBench, a comprehensive benchmark constructed from real-world interactions of 5 frontier models on 9 established benchmarks. Empirical results demonstrate that Qwen-AgentWorld significantly outperforms existing frontier models. (ii) Beyond foundation models, we further investigate two complementary paradigms through which world modeling enhances general agents. First, as a decoupled environment simulator, Qwen-AgentWorld supports scalable and controllable simulation of thousands of real-world environments for agentic RL, yielding gains that surpass real-environment training alone. Second, as a unified agent foundation model, world-model training acts as a highly effective warm-up that improves downstream performance across 7 agentic benchmarks. Code: https://github.com/QwenLM/Qwen-AgentWorld